End of training

README.md

@@ -0,0 +1,81 @@
+---
+library_name: transformers
+base_model: malmarjeh/mbert2mbert-arabic-text-summarization
+tags:
+- generated_from_trainer
+model-index:
+- name: resultmbert2mbert
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# resultmbert2mbert
+
+This model is a fine-tuned version of [malmarjeh/mbert2mbert-arabic-text-summarization](https://huggingface.co/malmarjeh/mbert2mbert-arabic-text-summarization) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8701
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 2.551         | 0.4263 | 500   | 1.0592          |
+| 1.1939        | 0.8525 | 1000  | 0.9787          |
+| 1.0979        | 1.2788 | 1500  | 0.9425          |
+| 1.0436        | 1.7050 | 2000  | 0.9134          |
+| 1.0132        | 2.1313 | 2500  | 0.9038          |
+| 0.9645        | 2.5575 | 3000  | 0.8905          |
+| 0.9608        | 2.9838 | 3500  | 0.8857          |
+| 0.9526        | 3.4101 | 4000  | 0.8931          |
+| 0.96          | 3.8363 | 4500  | 0.8838          |
+| 0.9254        | 4.2626 | 5000  | 0.8804          |
+| 0.9023        | 4.6888 | 5500  | 0.8724          |
+| 0.884         | 5.1151 | 6000  | 0.8754          |
+| 0.8496        | 5.5413 | 6500  | 0.8656          |
+| 0.85          | 5.9676 | 7000  | 0.8653          |
+| 0.8076        | 6.3939 | 7500  | 0.8668          |
+| 0.8119        | 6.8201 | 8000  | 0.8655          |
+| 0.7953        | 7.2464 | 8500  | 0.8676          |
+| 0.7719        | 7.6726 | 9000  | 0.8656          |
+| 0.7657        | 8.0989 | 9500  | 0.8710          |
+| 0.7446        | 8.5251 | 10000 | 0.8694          |
+| 0.7524        | 8.9514 | 10500 | 0.8658          |
+| 0.729         | 9.3777 | 11000 | 0.8699          |
+| 0.7338        | 9.8039 | 11500 | 0.8701          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,191 @@
+{
+  "_name_or_path": "malmarjeh/mbert2mbert-arabic-text-summarization",
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "bert-base-multilingual-cased",
+    "add_cross_attention": true,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "directionality": "bidi",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "pooler_fc_size": 768,
+    "pooler_num_attention_heads": 12,
+    "pooler_num_fc_layers": 3,
+    "pooler_size_per_head": 128,
+    "pooler_type": "first_token_transform",
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 119547
+  },
+  "decoder_start_token_id": 101,
+  "encoder": {
+    "_name_or_path": "bert-base-multilingual-cased",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "directionality": "bidi",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "pooler_fc_size": 768,
+    "pooler_num_attention_heads": 12,
+    "pooler_num_fc_layers": 3,
+    "pooler_size_per_head": 128,
+    "pooler_type": "first_token_transform",
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 119547
+  },
+  "eos_token_id": 102,
+  "is_encoder_decoder": true,
+  "max_length": 42,
+  "min_length": 5,
+  "model_type": "encoder-decoder",
+  "pad_token_id": 0,
+  "tie_encoder_decoder": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "vocab_size": 119547
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 101,
+  "eos_token_id": 102,
+  "max_length": 42,
+  "min_length": 5,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfbc9e21ee598e230616a236fcad734a7b9e4db44cfbfa0e1104e41aace2d3f0
+size 828562332

runs/Sep12_17-18-54_b466747592f1/events.out.tfevents.1726161641.b466747592f1.418.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9703abb444e1fe110b97dc198e7622910bf97daacbd95e2c15523229ec60d390
+size 13262

runs/Sep12_19-37-21_b466747592f1/events.out.tfevents.1726169869.b466747592f1.418.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c645c88825b5e2e2d88e51d5150856692637778c1617fa35c10602282d4de23f
+size 17629

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a06adf4c0e2e1e19e276808b3692ac8ca6e152eb4ef4759ce4d7561ae98618
+size 5176